docs: Document --model-reference flag for serverless create#631
docs: Document --model-reference flag for serverless create#631promptless[bot] wants to merge 9 commits into
Conversation
Add documentation for the new --model-reference flag that allows attaching models when creating serverless endpoints from templates.
![promptless[bot]](https://avatars.githubusercontent.com/in/979718?s=60&v=4){kind=small}
| @@ -159,6 +163,10 @@ Execution timeout in seconds. Jobs that exceed this duration are terminated. The | |||
| Environment variable in `KEY=VALUE` format. Use multiple `--env` flags to set multiple variables. When deploying from `--hub-id`, these values override the Hub release defaults. | |||
There was a problem hiding this comment.
Added --model-reference flag documentation based on PR #276 in runpodctl. The PR adds the flag to cmd/serverless/create.go with constraints: only works with --template-id (not --hub-id) and requires GPU compute type.
Source: runpod/runpodctl#276
|
Preview deployment for your docs. Learn more about Mintlify Previews.
💡 Tip: Enable Workflows to automatically generate PRs for you. |
Updates runpodctl serverless create documentation based on PR #284 which unifies all create paths onto the GraphQL saveEndpoint mutation: - Add --instance-id flag for CPU endpoints (default: cpu3g-4-16) - Add CPU endpoint example to examples section - Update --gpu-id to document both type IDs and pool IDs (auto-translation) - Update --name to document auto-generation when omitted - Fix flag names: --scale-by/--scale-threshold (not --scaler-type/--scaler-value) - Fix --idle-timeout range: 1-3600 (not 5-3600) - Document --network-volume-id and --network-volume-ids mutual exclusivity
PR runpod/runpodctl#289 removes the guard that rejected --model-reference with --hub-id. Correct the flag constraint and add a Hub+model example.
|
Just a reminder: If you'd like me to act on any feedback you have via Github comments, just type @Promptless in your suggestion and I'll get right on it! (I won't show up in the user dropdown, but I'll process any request that has @Promptless in the comment body.) |
|
@Promptless check if the changes you applied are up-to-date. |
|
I re-checked these changes against the current I verified
No PR merged since the last verification (2026-06-23) has changed the serverless create command surface: PR #292 and PR #281 touch adjacent serverless code but not this command, and PR #286 is still open. The docs are current as written. |
1 participant
Open this suggestion in Promptless to view citations and reasoning process
Adds documentation for the new --model-reference flag in runpodctl serverless create, which allows attaching models when deploying endpoints from templates (GPU compute only).
Trigger Events
Tip: Send Promptless a meeting transcript in Slack to generate doc updates 📝